© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109826
    Prev
    Next
    INDEX
    Explanations

    Scientific papers with numbers

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens—especially citation numbers, figure/table references, and decimal statistics—typically appearing in parentheses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horrifying
    -0.08
     logout
    -0.07
     bitk
    -0.07
    hx
    -0.07
    阅读次数
    -0.07
     bile
    -0.06
    _nested
    -0.06
    -picture
    -0.06
    둘
    -0.06
     AudioClip
    -0.06
    POSITIVE LOGITS
     touch
    0.07
     Essay
    0.07
    Redis
    0.06
     Paper
    0.06
    ेद
    0.06
     Apply
    0.06
    -categories
    0.06
    upid
    0.06
    .Symbol
    0.06
    touch
    0.06
    Activations Density 0.011%

    No Known Activations